Advanced Search

Query:

Fill in the form and click »Search«...

Format:

Display: entries per page entries

Zbl 0800.62521
Beran, Jan
Fitting long-memory models by generalized linear regression. (English)
[J] Biometrika 80, No. 4, 817-822 (1993). ISSN 0006-3444; ISSN 1464-3510/e

Summary: There is an increasing awareness of the importance of long-memory models in statistical applications. If long memory is present, it has to be taken into account in order to obtain reliable tests and confidence intervals. One obstacle to using models with long memory in routine statistical analysis has been the lack of easily available and sufficiently versatile statistical software. Here we propose a simple but flexible class of parametric models, which can be used to model such behaviour. We demonstrate that these models can be fitted by generalized linear regression. Standard statistical software packages can be used. A data example is discussed.

MSC 2000:: *62M10 Time series, etc. (statistics)
62J12 Generalized linear models

Keywords: fractional ARIMA; generalized linear models; long-range dependence; maximum likelihood estimation

Comment on this Item PDF MathML XML ASCII DVI PS BibTeX Online Ordering Article Journal Journal

	Scientific prize winners of the ICM 2010
	Overhang
	Lie groups, physics and geometry. An introduction for physicists, engineers and chemists.

Advanced Search

Zentralblatt MATH Berlin [Germany]